Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5043
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to Markov processes and queueing theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bounds
    -0.08
    bourg
    -0.07
    溶
    -0.07
    SSERT
    -0.07
    Ìĥ
    -0.07
    ash
    -0.07
    bett
    -0.07
    aura
    -0.07
     piger
    -0.07
    Shared
    -0.06
    POSITIVE LOGITS
     Asset
    0.08
     asset
    0.07
    Asset
    0.07
     Bell
    0.06
     Chand
    0.06
    (Func
    0.06
    vig
    0.06
     property
    0.06
     Magn
    0.05
     vel
    0.05
    Activations Density 0.011%

    No Known Activations